Microsoft Corporation has applied for a patent for a method of facial detection that attempts to locate a face within an image by using a complex algorithm for locating image features. The system is designed to primarily work with faces that are aimed directly at a camera or other optical device, and is expected to accommodate a slight degree of offset. The system is listed as invented by Toyama and Kentaro.
The abstract, filed with the U.S. Patent and Trademark Office, states: "The present invention is embodied in a system and method for detecting a face within an image using a relational template over a geometric distribution of a non-intensity image property. In general, the system of the present invention includes a hypothesis module for defining a sub-region in which to search for a face, a feature extraction module for extracting image feature values image based on a non-intensity image property, an averaging module for grouping the extracted image feature values into geometrically distributed facial regions, and a relational template module that uses a relational template and facial regions to determine whether a face has been detected. In a preferred embodiment the image property used is edge density, although other suitable properties (such as pixel color) may also be used. The method of the present invention includes performing feature extraction on the image based on an image property (such as edge density), grouping extracted image feature values into facial regions and using a relational template to determine whether a face has been detected."
The full application is available from the U.S. Patent and Trademark Office by searching for patent application number 6,792,135.